Classification of Citrus Huanglongbing Degree Based on CBAM-MobileNetV2 and Transfer Learning.

Citrus has become a pivotal industry for the rapid development of agriculture and increasing farmers' incomes in the main production areas of southern China. Knowing how to diagnose and control citrus huanglongbing has always been a challenge for fruit farmers. To promptly recognize the diagnosis of citrus huanglongbing, a new classification model of citrus huanglongbing was established based on MobileNetV2 with a convolutional block attention module (CBAM-MobileNetV2) and transfer learning. First, the convolution features were extracted using convolution modules to capture high-level object-based information. Second, an attention module was utilized to capture interesting semantic information. Third, the convolution module and attention module were combined to fuse these two types of information. Last, a new fully connected layer and a softmax layer were established. The collected 751 citrus huanglongbing images, with sizes of 3648 × 2736, were divided into early, middle, and late leaf images with different disease degrees, and were enhanced to 6008 leaf images with sizes of 512 × 512, including 2360 early citrus huanglongbing images, 2024 middle citrus huanglongbing images, and 1624 late citrus huanglongbing images. In total, 80% and 20% of the collected citrus huanglongbing images were assigned to the training set and the test set, respectively. The effects of different transfer learning methods, different model training effects, and initial learning rates on model performance were analyzed. The results show that with the same model and initial learning rate, the transfer learning method of parameter fine tuning was obviously better than the transfer learning method of parameter freezing, and that the recognition accuracy of the test set improved by 1.02~13.6%. The recognition accuracy of the citrus huanglongbing image recognition model based on CBAM-MobileNetV2 and transfer learning was 98.75% at an initial learning rate of 0.001, and the loss value was 0.0748. The accuracy rates of the MobileNetV2, Xception, and InceptionV3 network models were 98.14%, 96.96%, and 97.55%, respectively, and the effect was not as significant as that of CBAM-MobileNetV2. Therefore, based on CBAM-MobileNetV2 and transfer learning, an image recognition model of citrus huanglongbing images with high recognition accuracy could be constructed.

Changes in the relationship between vapour pressure deficit and water use efficiency with the drought recovery time: A case study of the Yellow River Basin.

Drought is a major driver of interannual variability in the gross primary productivity (GPP) of global terrestrial ecosystems, and drought recovery time has been widely used to assess ecosystem responses to drought. However, the response of the carbon-water coupled cycle to drought, especially changes in the correlation between drought intensity and carbon-water coupling throughout the recovery time, remains unclear. In this study, the Yellow River Basin (YRB) located mostly in drylands was the study area. We assessed the correlation between the standardized water vapour pressure deficit (VPD) and the water use efficiency of ecosystems (WUEe) and water use efficiency of canopies (WUEc) every month with the drought recovery time of GPP. We found that the drought intensity in the middle reach of the YRB (MYRB) was greater and the drought recovery time was longer than those in the upper reach (UYRB) and lower reach (LYRB) during the period from 2003 to 2017. In terms of the correlation between drought intensity and carbon-water coupling, the greater the VPD was, the lower the WUEc. In addition, the correlation of WUEc with VPD was higher than that of WUEe in most areas of the YRB, especially in the LYRB. On the watershed level, the correlation between the two types of WUE and VPD increased gradually with the recovery time, while the correlation between WUEc and VPD (mostly negative) changed more than the correlation between WUEe and VPD (mostly positive). Therefore, the response of WUEc to meteorological drought should be given more attention, especially during the middle and late stages of drought, since it exhibited an opposite signal compared to that of WUEe during drought recovery.

Comparison of multi-class and fusion of multiple single-class SegNet model for mapping karst wetland vegetation using UAV images.

Wetland vegetation classification using deep learning algorithm and unmanned aerial vehicle (UAV) images have attracted increased attentions. However, there exist several challenges in mapping karst wetland vegetation due to its fragmentation, intersection, and high heterogeneity of vegetation patches. This study proposed a novel approach to classify karst vegetation in Huixian National Wetland Park, the largest karst wetland in China by fusing single-class SegNet classification using the maximum probability algorithm. A new optimized post-classification algorithm was developed to eliminate the stitching traces caused by SegNet model prediction. This paper evaluated the effect of multi-class and fusion of multiple single-class SegNet models with different EPOCH values on mapping karst vegetation using UAV images. Finally, this paper carried out a comparison of classification accuracies between object-based Random Forest (RF) and fusion of single-class SegNet models. The specific conclusions of this paper include the followings: (1) fusion of four single-class SegNet models produced better classification for karst wetland vegetation than multi-class SegNet model, and achieved the highest overall accuracy of 87.34%; (2) the optimized post-classification algorithm improved classification accuracy of SegNet model by eliminating splicing traces; (3) classification performance of single-class SegNet model outperformed multi-class SegNet model, and improved classification accuracy (F1-Score) ranging from 10 to 25%; (4) Fusion of single-class SegNet models and object-based RF classifier both produced good classifications for karst wetland vegetation, and achieved over 87% overall accuracy.

Enantioselectivity and key residue of Herbaspirillum huttiense monooxygenase in asymmetric epoxidation of styrenes.

Styrene monooxygenases (SMOs) are powerful enzymes for the synthesis of enantiopure epoxides, but these SMOs have narrow substrate spectra, and the residues in controlling enantioselectivity of SMOs remains unclear. A monooxygenase from Herbaspirillum huttiense (HhMO) was found to have excellent enantioselectivities and diastereoselectivities in the epoxidation of unconjugated terminal alkenes. Here we found that HhMO could also transfer styrene into styrene epoxide with 75% ee, and it could also catalyze the epoxidation of styrene derivatives into the corresponding epoxides with enantioselectivities up to 99% ee. Meanwhile, site 199 in the substrate access channel of HhMO was found to play an important role in the controlling enantioselectivity of the epoxidation. The E199L variant catalyzed the epoxidation of styrene with > 99% ee. The identification of critical residue that affects the enantioselectivity of SMOs would thus be valuable for creating efficient monooxygenases for the preparation of essential enantiopure epoxides. KEY POINTS: • Bioexpoxidation of both conjugated and unconjugated alkenes by HhMO with excellent enantioselectivities. • Gating residue 199 played an essential role in controlling the enantioselectivity of SMO. • HhMO E199L catalyzed the epoxidation of styrenes with up to > 99% ee.